DeepFool: a simple and accurate method to fool deep neural networks
Authors:
- Seyed-Mohsen Moosavi-DezfooliSMSeyed-Mohsen Moosavi-Dezfooli
- Alhussein FawziAFAlhussein Fawzi
- Pascal FrossardPFPascal Frossard
Preprint
Abstract
State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images. Despite the importance of this phenomenon, no effective methods have been proposed to accurately compute the robustness of state-of-the-art deep classifiers to such perturbations on large-scale datasets. In this paper, we fill this gap and propose the DeepFool algorithm to efficiently compute perturbations that fool deep networks, and thus reliably quantify the robustness of these classifiers. Extensive experimental results show that our approach outperforms recent methods in the task of computing adversarial perturbations and making classifiers more robust.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Analysis of classifiers’ robustness to adversarial perturbationsMachine Learning, 2017
- A Deep Learning Network Approach to ab initio Protein Secondary Structure PredictionIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2014
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Least-Change Secant Update Methods for Underdetermined SystemsSIAM Journal on Numerical Analysis, 1990